legal-job-search

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill explicitly performs Deep Research and multi‑round Web Search fallbacks (SKILL.md and references/frameworks/*), fetching public third‑party content from sites like 中国裁判文书网, 企查查/天眼查, company websites and social media (知乎/脉脉) and instructs the agent to read and integrate those results into legal‑risk analyses and resume/strategy generation, which could allow untrusted external content to inject instructions.